Rafi

@karpathy @peteskomoroch oh LOL I love how everyone is slowly converging on the same use cases. I’ve been working on a personal knowledge engine for some time now. It’s more of an epistemic approach that helps me to surface connections between things i’m reading/working on over time.

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Lets go! Play pretext breaker 🎮 pretext-breaker.netlify.app

canon event, mark the day.

My dear front-end developers (and anyone who’s interested in the future of interfaces): I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept): Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

If you use GitHub (especially if you pay for it!!) consider doing this *immediately* Settings -> Privacy -> Disallow GitHub to train their models on your code. GitHub opted *everyone* into training. No matter if you pay for the service (like I do). WTH github.com/settings/copil…

GLM-OCR 0.9B model that beats Gemini on OCR benchmarks going live in 15 minutes to test it on real-world datasets and build some cool demos link: youtube.com/watch?v=_KCXD8…

It's time to bring 3D meshes into modern machine learning properly! 🛸 Our work solves the non-differentiability of the Exp map on meshes, enabling gradients to flow directly through geodesics. It’s differentiable, GPU-fast, and fully parallelised. circle-group.github.io/research/DSG

Happy Eid! 😊

It was great to see our name amongst the other “AI Native” companies during @Nvidia’s #GTC keynote. NVIDIA Isaac™ Lab helps us train reinforcement learning policies that enable the UMV to drive, jump, flip, and hop like a pro!

I've tried this out. Feels like a marriage between the web portal and the local IDE. I think this is the direction most agentic coding tools is moving.

calling it opensessions also...bring your own multiplexer (zellij, tmux, whatever) dropping the repo this week. ⭐ to get notified :p github.com/Ataraxy-Labs/o…

In the next version of Bun `Bun.WebView` programmatically controls a headless web browser in Bun

particle typography npx shadcn add @componentry/cursor-driven-particle-typography

Meet Raven:

Today we’re introducing Cheats in @Spielwerkapp Prompting has failed us. Most people don’t know what to type. AI unlocked a ton of skills for experts, but the rest of us kinda need a… cheat. Sound on!

STOP! DON’T LOOK OVER THERE at Elon Musk getting $38 billion in subsidies from your government! Look over HERE at a successful artist we don’t like buying herself some boots!

I want my Muslim brothers and sisters to repost this for the sake of Allah. They lied to her about Islam and she decided to read by herself and made this video. Let's get this viral to debunk the lies and propaganda that's being spread about our religion. ISLAM IS THE BEST! 🤍

This is the LAST day you can retweet this.

Different forms of idolatry